hunt-llm-ai

SKILLFlusso di lavorocommunity
v0.0.0elementalsoulsMITAggiornato 5 g faFonte →

Hunt LLM/AI feature bugs — prompt injection, indirect injection, exfiltration via tool-use/markdown, ASCII smuggling, agentic AI security (OWASP Agentic Apps 2026, ASI01-ASI10). Patterns: direct injection ('ignore previous instructions'), indirect injection via documents/web pages/email the model re

Community-submitted skill. Not yet reviewed by the Forge team. Full prompt content may not be available.Request review →
4kStelle del repo
1Client
1Formati
5 g faUltimo aggiornamento
Skill
Autoreelementalsouls
Versione0.0.0
LicenzaMIT
CategoriaFlusso di lavoro
Formatiskill.md
PromptApri (vedi la scheda Prompt)
Compatibilità
Claude✓ Supportato
Cursor—
Copilot—
ChatGPT—
Gemini—
Descrizione

Hunt LLM/AI feature bugs — prompt injection, indirect injection, exfiltration via tool-use/markdown, ASCII smuggling, agentic AI security (OWASP Agentic Apps 2026, ASI01-ASI10). Patterns: direct injection ('ignore previous instructions'), indirect injection via documents/web pages/email the model reads, ASCII smuggling (Unicode Tags block U+E0000-U+E007F, invisible to humans, decoded by the model)

Parole chiave
skillclaude